import pandas as pd
import seaborn as sns
import matplotlib.pyplot as plt
import numpy as np

# Import data
df = pd.read_csv("gapminder_clean.csv")

df.dropna(subset = ["CO2 emissions (metric tons per capita)"], inplace=True)
df.dropna(subset = ["gdpPercap"], inplace=True)

# Scatter plot
filtered_data = df[df["Year"] == 1962]
sns.scatterplot(data=filtered_data, x="CO2 emissions (metric tons per capita)", y="gdpPercap")

<AxesSubplot:xlabel='CO2 emissions (metric tons per capita)', ylabel='gdpPercap'>

# Pearson's r
from scipy.stats import pearsonr

corr, p_value = pearsonr(filtered_data["CO2 emissions (metric tons per capita)"], filtered_data["gdpPercap"])
print("\n Pearson correlation of 'CO2 emissions (metric tons per capita)' and gdpPercap, year 1962: \n","Correlation value: ",corr,"p-value: ",p_value)

 Pearson correlation of 'CO2 emissions (metric tons per capita)' and gdpPercap, year 1962: 
 Correlation value:  0.9260816725019472 p-value:  1.1286792210038754e-46

unfiltered_data = df[df["Year"] != 1962]
unfiltered_data.groupby(by=["Year"]).corrwith(other=df["CO2 emissions (metric tons per capita)"]).sort_values("gdpPercap", ascending=False)["gdpPercap"].head(1)

Year
1967    0.938792
Name: gdpPercap, dtype: float64

new_filtered_data = df[df["Year"] == 1967]

import plotly.express as px

fig = px.scatter(new_filtered_data, x='CO2 emissions (metric tons per capita)', y="gdpPercap", color="continent",
                 size='pop', hover_data=['Country Name'], title="CO2 emissions (metric tons per capita)' and gdpPercap. Year 1967")
fig.show()

What is the relationship between continent and 'Energy use (kg of oil equivalent per capita)'?

df.groupby("continent")["Energy use (kg of oil equivalent per capita)"].describe()

	count	mean	std	min	25%	50%	75%	max
continent
Africa	198.0	700.642721	628.227685	9.715410	377.734680	451.382174	746.247275	3071.774832
Americas	188.0	1703.620453	2377.181918	219.075497	556.033108	749.029108	1384.585146	14608.009868
Asia	185.0	1867.280336	2590.043514	86.903767	345.370792	760.140852	1987.087308	12122.050603
Europe	239.0	3110.604287	1768.370162	350.101258	2045.782889	2954.266739	3853.373983	14746.031338
Oceania	20.0	3980.314420	1123.410756	1791.461322	3143.501420	4044.850674	4783.650230	5868.347097

fig = px.box(df, x="Energy use (kg of oil equivalent per capita)", y="continent")
fig.show()

I need to know if the data satisfy parametric requirements to use parametric tests.

1. The population from which samples are drawn should be normally distributed. -> Shapiro-Wilk test.
2. Independence of cases: the sample cases should be independent of each other. -> I assume that this condition is satisfied.
3. Homogeneity of variance: Homogeneity means that the variance among the groups should be approximately equal. -> Levene test

americas_energy = df[df["continent"] == "Americas"]["Energy use (kg of oil equivalent per capita)"].dropna()
oceania_energy = df[df["continent"] == "Oceania"]["Energy use (kg of oil equivalent per capita)"].dropna()
africa_energy = df[df["continent"] == "Africa"]["Energy use (kg of oil equivalent per capita)"].dropna()
europe_energy = df[df["continent"] == "Europe"]["Energy use (kg of oil equivalent per capita)"].dropna()
asia_energy = df[df["continent"] == "Asia"]["Energy use (kg of oil equivalent per capita)"].dropna()

import scipy.stats as stats
#The Shapiro-Wilk test tests the null hypothesis that the data was drawn from a normal distribution.
print("\n",
stats.shapiro(americas_energy),"\n",
stats.shapiro(oceania_energy),"\n",
stats.shapiro(africa_energy),"\n",
stats.shapiro(europe_energy),"\n",
stats.shapiro(asia_energy))

 ShapiroResult(statistic=0.5632225871086121, pvalue=1.5868403861741054e-21) 
 ShapiroResult(statistic=0.9818098545074463, pvalue=0.9552662372589111) 
 ShapiroResult(statistic=0.6753993034362793, pvalue=2.724574480963581e-19) 
 ShapiroResult(statistic=0.889901876449585, pvalue=3.4700315537650184e-12) 
 ShapiroResult(statistic=0.6609910130500793, pvalue=4.943039538112358e-19)

Shapiro-Wilk tests: rejected 4/5 null hypotheses. Data is not normal distributed

import scipy.stats as stats
#The Levene test tests the null hypothesis that all input samples are from populations with equal variances. 
stats.levene(*[americas_energy, oceania_energy, africa_energy,europe_energy, asia_energy], center='median', proportiontocut=0.05)

LeveneResult(statistic=12.113489871462216, pvalue=1.4250677574810339e-09)

Leneve test: rejected null hypothesis.

# The Kruskal-Wallis H-test tests the null hypothesis that the population median of all of the groups are equal. 
fvalue, pvalue = stats.kruskal(*[americas_energy, oceania_energy, africa_energy,europe_energy, asia_energy])
print(fvalue, pvalue)

302.0114932359461 3.989307514095183e-64

Kruskal-Wallis H-test: rejected null hypothesis.

# Post hoc pairwise test for multiple comparisons of mean rank sums (Dunn’s test). 
# May be used after Kruskal-Wallis one-way analysis of variance by ranks to do pairwise comparisons 
import scikit_posthocs as sp
dunn_test = sp.posthoc_dunn([americas_energy, oceania_energy, africa_energy,europe_energy, asia_energy])
dunn_test.columns =["americas_energy","oceania_energy","africa_energy","europe_energy","asia_energy"]
dunn_test.index =["americas_energy","oceania_energy","africa_energy","europe_energy","asia_energy"]
dunn_test

	americas_energy	oceania_energy	africa_energy	europe_energy	asia_energy
americas_energy	1.000000e+00	5.358423e-08	6.438289e-10	1.025511e-20	1.858753e-01
oceania_energy	5.358423e-08	1.000000e+00	4.148905e-16	1.125350e-01	1.779352e-09
africa_energy	6.438289e-10	4.148905e-16	1.000000e+00	9.844921e-58	1.479379e-06
europe_energy	1.025511e-20	1.125350e-01	9.844921e-58	1.000000e+00	1.130215e-26
asia_energy	1.858753e-01	1.779352e-09	1.479379e-06	1.130215e-26	1.000000e+00

fig = px.imshow(dunn_test)
fig.show()

Asia's and Americas' energy use means are similar. Oceania's and Europe's energy use means are similar.

Is there a significant difference between Europe and Asia with respect to 'Imports of goods and services (% of GDP)' in the years after 1990? (Stats test needed)

europe_and_asia_after_1990 = df[((df["continent"] == "Europe") |
                                 (df["continent"] == "Asia")) & (df["Year"] > 1990) & 
                                (df['Imports of goods and services (% of GDP)'] < 97 ) ] # Deleted Outliers (Singapore is an exception)
europe_and_asia_after_1990.groupby("continent")["Imports of goods and services (% of GDP)"].describe()

	count	mean	std	min	25%	50%	75%	max
continent
Asia	93.0	41.713928	23.454248	0.079506	25.393531	38.831290	58.350047	96.742045
Europe	111.0	41.761071	16.818978	17.345130	28.462519	37.691245	51.129504	88.512248

fig = px.box(europe_and_asia_after_1990, x="Imports of goods and services (% of GDP)", y="continent", hover_data=['Country Name', "Year"])
fig.show()

europe_imports =europe_and_asia_after_1990[europe_and_asia_after_1990["continent"] == "Europe"]["Imports of goods and services (% of GDP)"].dropna()
asia_imports = europe_and_asia_after_1990[europe_and_asia_after_1990["continent"] == "Asia"]["Imports of goods and services (% of GDP)"].dropna()
print("\n", stats.shapiro(europe_imports), "\n", stats.shapiro(asia_imports))
stats.levene(*[europe_imports,asia_imports], center='median', proportiontocut=0.05)

 ShapiroResult(statistic=0.9278804063796997, pvalue=1.486705423303647e-05) 
 ShapiroResult(statistic=0.9704142212867737, pvalue=0.032892148941755295)

LeveneResult(statistic=9.881593643140368, pvalue=0.0019207769451392669)

Shapiro-Wilk tests: rejected 1/2 null hypotheses. Data is not normal distributed Leneve test: rejected null hypothesis.

#The Mann-Whitney U test is used to compare differences between two independent groups when the dependent variable is either ordinal or continuous, but not normally distributed. 
stats.mannwhitneyu(x=europe_imports, y=asia_imports)

MannwhitneyuResult(statistic=5034.0, pvalue=0.3811649093378452)

Can not reject the null hypothesis of identical average scores.

What is the country (or countries) that has the highest 'Population density (people per sq. km of land area)' across all years? (i.e., which country has the highest average ranking in this category across each time point in the dataset?)

fig = px.line(df, x="Year", y="Population density (people per sq. km of land area)", color="continent",
              line_group="Country Name", hover_name="Country Name", 
              title="Population density (people per sq. km of land area) across all years")
fig.show()

What country (or countries) has shown the greatest increase in 'Life expectancy at birth, total (years)' since 1962?

grouped_df = df.groupby("Country Name")
first_values = grouped_df.first()
first_values = first_values.reset_index()
df_1 = first_values[["Country Name","Life expectancy at birth, total (years)"]]
last_values = grouped_df.last()
last_values = last_values.reset_index()
df_2 = last_values[["Country Name","Life expectancy at birth, total (years)"]]
df_2.rename(columns={"Life expectancy at birth, total (years)": "last"}, errors="raise")
df_3 =pd.concat([df_1,df_2], axis=1)
df_3.columns = ['Country Name', 'first_life', 'drop', "last_life"]
df_3 = df_3.drop("drop", axis=1)
df_3["delta"] = df_3['last_life'].sub(df_3['first_life'], axis = 0)
df_3.sort_values(by=['delta'], ascending=False).head(5)[["Country Name","delta"]]

	Country Name	delta
118	Tunisia	30.860756
81	Nepal	30.599634
24	China	29.942098
88	Oman	27.016537
99	Saudi Arabia	26.650561

df_3_greater_than_zero = df_3[df_3["delta"] > 0] #Removed negative values because cause error
fig = px.scatter(df_3_greater_than_zero, x='delta', y="last_life", color="delta", title="Changes in life expectancy at birth",
                 size='delta', hover_data=['Country Name'],
                labels={
                     "last_life": "Life expectancy at birth, total (years). Last record.",
                     "delta": "Difference between first and last record, (years)"
                 },)
fig.show()